Start here
The word “agent” is used to sell everything. Underneath sits a fairly simple loop: a model picks an action, a program runs it, a result comes back. What matters is the limits you put around it.
Development
Three measures summarise what a visitor feels: how fast the main content appears, how responsive the page is to interaction, how stable the layout is. What they mean, how to measure them, and where to start.
Agents, document search, choosing models: how these systems work, and where they fail.
Designing and measuring web applications: performance, architecture, practices that last.
Deploying and operating: Kubernetes, GitOps, continuous delivery, at the scale of a small team.
Threats, hardening, supply chain: what really protects, and what only reassures.
2026
Development
A model has not read your documents. RAG means finding the right passages before you ask it the question. Chunking, embeddings, hybrid search, citations: where quality is won and where it is lost.
2026
AI
Host a model yourself or pay for an API: the right answer depends on five criteria you can examine one by one. Real cost, privacy, latency, licence and dependency, without dogma.
2026
Security
A model does not firmly tell an instruction from a piece of data: it is all text. As long as that holds, an agent reading outside content can be hijacked. You cannot remove the flaw, you can bound what it can cause.
Every article appears in the RSS feed, in full. A feed reader is the simplest way never to miss one, with no account.